TMElyralab · First MLX build 5 Jun 2026
MuseTalk
MLX
Image mit
A image to image model from TMElyralab, with 3 MLX builds, from fp16 to 8-bit.
- Parameters
- — Not published
- Quantisation
- fp16 MuseTalk-1.5-fp16
- Memory needed
- — GB Estimate, unified memory
- Download
- — Weights, estimated
- Downloads
- 1.3K This build, last 30 days
- Task
- Image to image Image
- MLX builds
- 3 On mlx-community
- Devices
- Mac Apple silicon
Memory
Hugging Face does not list a weights size for this build, so there is no memory estimate.
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/MuseTalk-1.5-fp16MLX builds
3 on mlx-community| MuseTalk-1.5-fp16 | fp16 | — | — | 1.3K |
|---|---|---|---|---|
| MuseTalk-1.5-q4 | 4-bit | — | — | 1.2K |
| MuseTalk-1.5-q8 | 8-bit | — | — | 399 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.